Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77270
    Prev
    Next
    INDEX
    Explanations

    exist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .RO
    -0.08
    味
    -0.08
    STAR
    -0.08
    inei
    -0.08
     gel
    -0.07
    aina
    -0.07
    ून
    -0.07
     הש
    -0.07
    .Localization
    -0.07
    _again
    -0.07
    POSITIVE LOGITS
     olyan
    0.10
    န္
    0.08
     eyeb
    0.08
    $s
    0.08
    }s
    0.08
    )i
    0.08
    gun
    0.08
    	i
    0.08
    élé
    0.07
     Blind
    0.07
    Activations Density 0.045%

    No Known Activations